Missing data imputation in hourly CO measurements for air quality monitoring: a case study in the city of Salvador, Brazil
Taiane Campos Braga de Assis, Cristiano Hora Fontes, Édler Lins Albuquerque · 2026
Read Missing data imputation in hourly CO measurements for air quality monitoring: a case study in the city of Salvador, Brazil by Taiane Campos Braga de Assis, Cristiano Hora Fontes, Édler Lins Albuquerque (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13212405.txt.
Description
Taiane Campos Braga de Assis and co-authors address, in 2026, gaps in hourly carbon monoxide readings from an air monitor in Salvador, Brazil. Missing stretches arise from power cuts, calibration, and transmission faults, and they weaken pollution records used for policy.
The team hid real data in artificial gaps lasting one to three days, then tested three models at filling them in. A boosted-tree model scored slightly best on error measures, though recurrent neural networks described more gaps consistently, and neither lead was statistically firm. Filled values showed no systematic bias and kept the series' daily and seasonal patterns, supporting model-based repair of monitoring records.
Catalog record
| CREATOR | Taiane Campos Braga de Assis, Cristiano Hora Fontes, Édler Lins Albuquerque |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |